Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1909 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.4643. Min Act: -0.1700
Data Index: 1431857 (Python Code)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3992. Min Act: -0.1700
Data Index: 1366127 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3502. Min Act: -0.1700
Data Index: 1430421 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3502. Min Act: -0.1700
Data Index: 1620573 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3338. Min Act: -0.1700
Data Index: 1607669 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3338. Min Act: -0.1700
Data Index: 1502487 (Python Code)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3338. Min Act: -0.1700
Data Index: 37985 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3174. Min Act: -0.1700
Data Index: 1527813 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2845. Min Act: -0.1700
Data Index: 639704 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3009. Min Act: -0.1700
Data Index: 1550018 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3009. Min Act: -0.1700
Data Index: 1490708 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3009. Min Act: -0.1700
Data Index: 1256982 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.3009. Min Act: -0.1700
Data Index: 805065 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2845. Min Act: -0.1700
Data Index: 1572915 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2845. Min Act: -0.1700
Data Index: 1385129 (Python Code)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2845. Min Act: -0.1700
Data Index: 1547247 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2680. Min Act: -0.1700
Data Index: 1456075 (Python Code)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2680. Min Act: -0.1700
Data Index: 706212 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2515. Min Act: -0.1700
Data Index: 1365778 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4643. Min Range: -2.4643
Max Act: 2.2515. Min Act: -0.1700
Data Index: 1593519 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19